© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6658
    Prev
    Next
    INDEX
    Explanations

    principles and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aback
    1.16
    ación
    1.11
    قدم
    1.11
    ráf
    1.10
     extravag
    1.10
    Ӹ
    1.09
     agradable
    1.06
    ﺓ
    1.06
    ibouti
    1.03
    कारात्मक
    1.02
    POSITIVE LOGITS
     principles
    1.52
     principle
    1.48
     Principle
    1.41
     rules
    1.38
     Principles
    1.37
     법칙
    1.18
     Rules
    1.14
    ма
    1.13
    principles
    1.13
    Rules
    1.10
    Activations Density 0.423%

    No Known Activations